OR: How and why is it the ChatGPT has a more coherent "understanding" of the role of the printing press in history than Walter Isaacson, Eric Schmidt, and Tyler Cowen?
Here’s a video where mega-billionaire and former Google CEO, Eric Schmidt, is interviewed by Walter Isaacson, former editor of Time magazine, and biographer of Henry Kissenger, Albert Einstein, and Steve Jobs, about “the Consequences of an A. I. Revolution.”
Starting at about 1:33 Isaacson mentions the book that Schmidt co-authored with Henry Kissinger and Daniel Huttenlocher, The Age of AI: And Our Human Future, mentioning how it “compares this to the advent of the Englistenment, something I think that was spurred to by great technology, which is movable type printing presses that Guttenberg did, compare what’s happening now to the Englightenment.” Schmidt replies, “We do not have a philosophical basis for interacting with an intelligence that’s near our ability, but non-human.”
Schmidt’s right about that. And we’re not going create that philosophy as long as we continue to credit the Enlightenment to Gutenberg, if, in fact, that’s what’s going on here. Isaacson’s phrase “spurred on by” leaves a great deal wiggle room. So, these guys can wiggle. But they’re wiggling around the wrong center.
Again, with the printing press
Nor are they alone in this comparison. I willing to believe that it’s rife among the chattering classes, though I have no evidence. But I can offer another data point.
A few days ago Tyler Cowen had a post entitled, Existential risk, AI, and the inevitable turn in human history. He said:
Hardly anyone you know, including yourself, is prepared to live in actual “moving” history. It will panic many of us, disorient the rest of us, and cause great upheavals in our fortunes, both good and bad. In my view the good will considerably outweigh the bad (at least from losing #2, not #1), but I do understand that the absolute quantity of the bad disruptions will be high.
I am reminded of the advent of the printing press, after Gutenberg. Of course the press brought an immense amount of good, enabling the scientific and industrial revolutions, among many other benefits. But it also created writings by Lenin, Hitler, and Mao’s Red Book. It is a moot point whether you can “blame” those on the printing press, nonetheless the press brought (in combination with some other innovations) a remarkable amount of true, moving history. How about the Wars of Religion and the bloody 17th century to boot? Still, if you were redoing world history you would take the printing press in a heartbeat. Who needs poverty, squalor, and recurrences of Ghenghis Khan-like figures?
But since we are not used to living in moving history, and indeed most of us are psychologically unable to truly imagine living in moving history, all these new AI developments pose a great conundrum. We don’t know how to respond psychologically, or for that matter substantively.
I appreciate Cowen’s reference to “moving” history, which is something I’ve written about: Things change, but sometimes they don’t: On the difference between learning about and living through [revising your priors and the way of the world]. There I talk about the effect that fall of the Soviet Union had on my own sense of the world along with disruptive events in my intellectual life, discovering the structure of “Kubla Khan” and the collapse of symbolic computing (see also my recent 3QD essay, From “Kubla Khan” through GPT and beyond).
iAnd I suppose I should overlook Cowen’s talk of the printing press “creating” various “writings by Lenin, Hitler, and Mao’s Red Book.” He doesn’t mean that literally, but figuratively.
Prior to and deeper than the printing press
THAT’s the problem. The printing press cannot and did not create thought, even figuratively. It was important in disseminating thought, which obviously is very important. And that dissemination certainly played a role in the larger processes of innovation. But it did not itself play the role of intellectual catalyst.
In our essay, The Evolution of Cognition, David Hays and I assigned that role to the introduction of algorithmic calculation (using the Arabic notation) into Europe early in the 13th century and its subsequent development and exploitation. We said:
The amazing thing about algorithmic calculation is that it always works. If two, or three, or four, people make the calculation, they all come up with the same answer. This is not true of non-algorithmic calculation, where procedures were developed on a case-by-case basis with no statements of general principles. In this situation some arithmeticians are going to get right answers more often than others, but no one can be sure of hitting on the right answer every time.
This ad hoc intellectual style, moreover, would make it almost impossible to sense the underlying integrity of the arithmetic system, to display its workings independently of the ingenious efforts of the arithmetician. The ancients were as interested in magical properties of numbers as in separating the odd from the even (Marrou 179-181). By interposing explicit procedures between the arithmetician and his numbers, algorithmic systems contribute to the intuition of a firm subject-object distinction. The world of algorithmic calculations is the same for all arithmeticians and is therefore essentially distinct from them. It is a self-contained universe of objects (numbers) and processes (the algorithms). The stage is now set for experimental science. Science presents us with a mechanistic world and adopts the experimental test as its way of maintaining objectivity. A theory is true if its conceptual mechanism (its "algorithm") suggests observations which are subsequently confirmed by different observers. Just as the results of calculation can be checked, so can theories.
Algorithmic calculation is an intellectual device and, as such, can play a direct role in the development of other intellectual devices. Hays and I go on to discuss the impact of algorithmic calculation on our sense of mechanism:
The world of classical antiquity was altogether static. The glories of Greece were Platonic ideals and Euclidean geometry, Phidias's sculptures and marble temples. Although Mediterranean antiquity knew the wheel, it did not know mechanism. Water mills were tried, but not much used. Hero of Alexandria invented toys large and small with moving parts, but nothing practical came of them. Historians generally assert that the ancients did not need mechanism because they had surplus labor, but it seems to us more credible to say that they did not exploit mechanisms because their culture did not tolerate the idea. With the little Renaissance, the first machine with two co-ordinated motions, a sawmill that both pushed the log and turned the saw blade, turned up (White 1978: 80). Was it something in Germanic culture, or the effect of bringing together the cultures of Greece and Rome, of Islam and the East, that brought a sense of mechanism? We hope to learn more about this question, but for the moment we have to leave it unanswered.
What we can see is that generalizations of the idea of mechanism would be fruitful for technology (and they were), but that it would take an abstraction to produce a new view of nature. The algorithm can be understood in just this way. If its originators in India disregarded mechanism, and the north European developers of mechanism lacked the abstraction, it would only be the accidental propinquity of the two that generated a result. Put the abstract version together in one culture with a host of concrete examples, and by metaphor lay out the idea of the universe as a great machine. What is characteristic of machines is their temporality; a static machine is not a machine at all. And, with that, further add the co-ordination of motions as in the sawmill. Galileo discovered that force alters acceleration, not velocity (a discovery about temporality) and during the next few centuries mechanical clocks were made successfully. The notion of a clockwork universe spread across Europe (note that the Chinese had clockworks in the 11th Century, but never developed the notion of a clockwork universe, cf. Needham 1981). For any machine, it is possible to make functional diagrams and describe the relative motions of the parts; and the theories of classical science can be understood as functional diagrams of nature, with descriptions of the relative motions of the parts.
Now we have the beginnings of a coherent story about the intellectual sources of the Enlightenment. It’s a story about ideas engendering other ideas.
The conceptual universe in which it is not only acceptable but routine and conventional to talk about the printing press engendering ideas, that conceptual universe is based on an incoherent underlying conceptual ontology. That ontology is of little use in helping us to understand the implications of computational intelligence. In fact, I can imagine that it is at least partially responsible for the widespread belief that we are victims of the inevitable march of technology.
While Tyler understands that it is ideas that create technology in the small – hence his program of Emergent Ventures. In the large, he believes that we are driven by technology.
What ChatGPT thinks about calculation and the printing press
Near the end of March I asked ChatGPT about the importance of the printing press and about several other things – metaphor and analogy, arithmetic, the clockwork universe, and the steam engine. This is from that interaction, which I posted in full on March 29:
Can you draw connections between the idea of the clockwork universe, printing technology, and arithmetic?
There are several connections that can be drawn between the idea of the clockwork universe, printing technology, and arithmetic.
First, the clockwork universe idea suggests that the universe operates according to predictable, mechanical laws. This idea helped to fuel the development of modern science and technology, including printing technology and arithmetic. By understanding the world as a vast machine that operates according to predictable laws, thinkers were able to develop systems for organizing and communicating information that could be used to advance knowledge and promote progress.
Printing technology, in particular, played a critical role in disseminating knowledge and information on a large scale. The printing press made it possible to reproduce written materials in large quantities, making it easier to share ideas and spread knowledge. This helped to fuel the growth of science, philosophy, and other areas of intellectual inquiry, and contributed to the development of the clockwork universe idea.
Similarly, arithmetic played a critical role in the development of the clockwork universe idea. By understanding the world in terms of mathematical laws and principles, thinkers were able to develop a more precise and rigorous understanding of the universe. The use of Arabic numerals, in particular, allowed for the development of more efficient and versatile systems for performing calculations, which helped to accelerate the growth of science and technology.
Overall, the connections between the clockwork universe idea, printing technology, and arithmetic highlight the importance of developing efficient and versatile systems for organizing and communicating information. By understanding the world as a vast machine that operates according to predictable laws, and by developing systems for sharing and processing information more efficiently, thinkers were able to accelerate progress and drive innovation in a wide range of fields.
It would seem that in this matter the machine is more coherent than Walter Isaacson, Eric Schmidt, and Tyler Cowen.
No comments:
Post a Comment